Correlating call data and speech recognition information in a telephony application

• US 6,931,105 B2
• Filed: 08/19/2002
• Issued: 08/16/2005
• Est. Priority Date: 08/19/2002
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Muterspaugh, Kevin James, Groves, Christopher Ryan
• Primary Examiner(s): Foster, Roland G.
• Application Number:
  US10/223,465
• Publication Number:
  US 20040032933A1
• Time in Patent Office: 1,093 Days
• Field of Search: 379 8801- 8804, 704/231, 704/240, 704/243, 704/246, 704/251, 704/270, 704/270.1, 704/275, 704/253
• US Class Current: 379/88.03
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 1/271 controlled by voice recognition

Abstract

A method for improving the recognition confidence of alphanumeric spoken input, suitable for use in a speech recognition telephony application such as a voice response system. An alphanumeric candidate is determined from the spoken input, which may be the best available representation of the spoken input. Recognition confidence is compared with a preestablished threshold. If the recognition confidence exceeds the threshold, the alphanumeric candidate is selected to represent the spoken input. Otherwise, present call data associated with the spoken input is determined. Call data may include automatic number identification (ANI) information, caller-ID information, and/or dialed number information service (DNIS) information. Information associated with the alphanumeric candidate and information associated with the present call data are correlated in order to select alphanumeric information that best represents the spoken input.

Claims

1. A method for improving the recognition confidence of alphanumeric spoken input, suitable for use in a telephony application, said method comprising the steps of:

determining an alphanumeric candidate from spoken input;

determining present call data associated with a source of the spoken input;

constructing a plurality of alphanumeric possibilities based on the alphanumeric candidate;

recalling historical call data associated with each alphanumeric possibility;

comparing the present call data with the historical call data associated with each alphanumeric possibility; and

selecting the alphanumeric possibility whose historical call data best matches the present call data, to represent the spoken input.

2. The method of claim 1, wherein the present call data includes automatic number identification information.

3. The method of claim 1, wherein the present call data includes caller-ID information.

4. The method of claim 1, wherein the present call data includes dialed number information service information.

5. The method of claim 1, wherein the present call data includes dialed number information service information and automatic number identification information.

6. The method of claim 1, wherein the present call data includes dialed number information service information and caller-ID information.

7. The method of claim 1, wherein the present call data includes an Internet address.